Agentlas Browser Automation (/agentlas-browser, /hep-browser)

SkillWeb & browsing

This skill gives your agent a real browser to work in. Once added, it can open and interact with web pages, fill in forms, and capture what appears on screen so you can see the result. It is useful when a task needs more than reading a page, such as working through a form or showing visual evidence.

Available today. Use it from your connected AI after setup.

After adding it, give your agent a link or a question and describe the task you want done in the browser. Typing /agentlas-browser followed by a link or query kicks it off.

Then ask your AI: use the Agentlas Browser Automation (/agentlas-browser, /hep-browser) skill

What your AI can do with it

  • Open and render web pages that need a browser
  • Fill in and step through online forms
  • Capture what is on screen as evidence of a task
  • Handle browser-required tasks end to end, not just read page text
  • Start a browser task from a link or a question you provide

What this skill tells your AI

The instructions your AI receives, as published by agentlas-ai/agentlas-os in skills/agentlas-browser/SKILL.md and read by ahel’s review.

Browser interaction and headless/CDP automation runner for Agentlas tasks. Alias for /hep-browser and /agentlas browser.

Signals

GitHub stars
1k
Forks
103
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
agentlas-browser
Source
github.com/agentlas-ai/agentlas-os